Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to people or their relationships within the narrative

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ughters
    -0.17
    leurs
    -0.16
    createFrom
    -0.15
    adoras
    -0.15
    atori
    -0.15
    tober
    -0.15
    ÎŁÎ¹
    -0.14
    andır
    -0.14
    ervas
    -0.14
     quienes
    -0.14
    POSITIVE LOGITS
     guy
    0.27
     man
    0.21
     young
    0.19
     woman
    0.18
     him
    0.17
     dude
    0.17
     unnamed
    0.16
     Mr
    0.16
     gentleman
    0.15
     boy
    0.15
    Act Density 0.271%

    No Known Activations